Data pixelization for predicting completion time of events

Nowadays, a company uses many sensors to record its entire activity process; the recorded data are called event-log. However, event-log prevalently contains discrete data that many powerful machine-learning algorithms are unable to deal with. One-hot encoding is an outstanding method for transforming discrete data into a binary vector. Nonetheless, if there are many distinct values, the problem of dimensionality will be incurred. To tackle this issue, we propose a new approach, called the Pixelization method, which transforms event data into images. We experimentally performed causal inference for prediction of pixels (representing the processing time of each event) by using a generative model with our novel convolution technique. We compared our approach with a baseline method, one-hot encoding, and an entity-embedded approach combined with a neural network model. The results showed that our approach outperforms the state-of-the-art methods in terms of accuracy.